Neuroimaging feature extraction using a neural network classifier for imaging genetics.

BACKGROUND: Dealing with the high dimension of both neuroimaging data and genetic data is a difficult problem in the association of genetic data to neuroimaging. In this article, we tackle the latter problem with an eye toward developing solutions that are relevant for disease prediction. Supported by a vast literature on the predictive power of neural networks, our proposed solution uses neural networks to extract from neuroimaging data features that are relevant for predicting Alzheimer's Disease (AD) for subsequent relation to genetics. The neuroimaging-genetic pipeline we propose is comprised of image processing, neuroimaging feature extraction and genetic association steps. We present a neural network classifier for extracting neuroimaging features that are related with the disease. The proposed method is data-driven and requires no expert advice or a priori selection of regions of interest. We further propose a multivariate regression with priors specified in the Bayesian framework that allows for group sparsity at multiple levels including SNPs and genes. RESULTS: We find the features extracted with our proposed method are better predictors of AD than features used previously in the literature suggesting that single nucleotide polymorphisms (SNPs) related to the features extracted by our proposed method are also more relevant for AD. Our neuroimaging-genetic pipeline lead to the identification of some overlapping and more importantly some different SNPs when compared to those identified with previously used features. CONCLUSIONS: The pipeline we propose combines machine learning and statistical methods to benefit from the strong predictive performance of blackbox models to extract relevant features while preserving the interpretation provided by Bayesian models for genetic association. Finally, we argue in favour of using automatic feature extraction, such as the method we propose, in addition to ROI or voxelwise analysis to find potentially novel disease-relevant SNPs that may not be detected when using ROIs or voxels alone.

Investigating the relationship between the Bayes factor and the separation of credible intervals.

We examined the relationship between the Bayes factor and the separation of credible intervals in between- and within-subject designs under a range of effect and sample sizes. For the within-subject case, we considered five intervals: (1) the within-subject confidence interval of Loftus and Masson (1994); (2) the within-subject Bayesian interval developed by Nathoo et al. (2018), whose derivation conditions on estimated random effects; (3) and (4) two modifications of (2) based on a proposal by Heck (2019) to allow for shrinkage and account for uncertainty in the estimation of random effects; and (5) the standard Bayesian highest-density interval. We derived and observed through simulations a clear and consistent relationship between the Bayes factor and the separation of credible intervals. Remarkably, for a given sample size, this relationship is described well by a simple quadratic exponential curve and is most precise in case (4). In contrast, interval (5) is relatively wide due to between-subjects variability and is likely to obscure effects when used in within-subject designs, rendering its relationship with the Bayes factor unclear in that case. We discuss how the separation percentage of (4), combined with knowledge of the sample size, could provide evidence in support of either a null or an alternative hypothesis. We also present a case study with example data and provide an R package 'rmBayes' to enable computation of each of the within-subject credible intervals investigated here using a number of possible prior distributions.

CD8 + T cell infiltration is associated with improved survival and negatively correlates with hypoxia in clear cell ovarian cancer.

Unlike other histological types of epithelial ovarian carcinoma, clear cell ovarian carcinoma (CCOC) has poor response to therapy. In many other carcinomas, expression of the hypoxia-related enzyme Carbonic anhydrase IX (CAIX) by cancer cells is associated with poor prognosis, while the presence of CD8 + tumor-infiltrating lymphocytes (TIL) is positively prognostic. We employed [18F]EF5-PET/CT imaging, transcriptome profiling, and spatially-resolved histological analysis to evaluate relationships between CAIX, CD8, and survival in CCOC. Tissue microarrays (TMAs) were evaluated for 218 cases in the Canadian COEUR study. Non-spatial relationships between CAIX and CD8 were investigated using Spearman rank correlation, negative binomial regression and gene set enrichment analysis. Spatial relationships at the cell level were investigated using the cross K-function. Survival analysis was used to assess the relationship of CAIX and CD8 with patient survival for 154 cases. CD8 + T cell infiltration positively predicted survival with estimated hazard ratio 0.974 (95% CI 0.950, 1000). The negative binomial regression analysis found a strong TMA effect (p-value < 0.0001). It also indicated a negative association between CD8 and CAIX overall (p-value = 0.0171) and in stroma (p-value = 0.0050) but not in tumor (p-value = 0.173). Examination of the spatial association between the locations of CD8 + T cells and CAIX cells found a significant amount of heterogeneity in the first TMA, while in the second TMA there was a clear signal indicating negative spatial association in stromal regions. These results suggest that hypoxia may contribute to immune exclusion, primarily mediated by effects in stroma.

Improving Rates of Germline BRCA Mutation Testing for Patients With Ovarian Cancer in Vancouver Island, British Columbia, Canada.

PURPOSE: Despite more than a decade of endorsement from multiple international cancer authorities advocating all women with ovarian cancer be offered germline breast cancer (BRCA) gene testing, British Columbia Cancer Victoria was not meeting this target. A quality improvement project was undertaken with the aim of increasing completed BRCA testing rates for all eligible patients seen at British Columbia Cancer Victoria to > 90% by 1 year from April 2016. METHODS: A current state analysis was completed, and multiple change ideas were developed, including education of medical oncologists, referral process update, initiating a group consenting seminar, and engagement of a nurse practitioner to lead the seminar. We used a retrospective chart audit from December 2014 to February 2018. On April 15, 2016, we initiated our Plan, Do, Study, Act (PDSA) cycles and completed them on February 28, 2018. We evaluated sustainability through an additional retrospective chart audit from January 2021 to August 2021. RESULTS: Patients with completed germline BRCA genetic testing climbed from an average of 58%-89% per month. Before our project, patients waited on average 243 days (± 214) for their genetic test results. After implementation, patients received results within 118 days (± 98). This was sustained with an average of 83% of patients per month having completed germline BRCA testing almost 3 years after project completion. CONCLUSION: Our quality improvement initiative resulted in a sustained increase in germline BRCA test completion for eligible patients with ovarian cancer.

A Review of Bayesian Hypothesis Testing and Its Practical Implementations.

We discuss hypothesis testing and compare different theories in light of observed or experimental data as fundamental endeavors in the sciences. Issues associated with the p-value approach and null hypothesis significance testing are reviewed, and the Bayesian alternative based on the Bayes factor is introduced, along with a review of computational methods and sensitivity related to prior distributions. We demonstrate how Bayesian testing can be practically implemented in several examples, such as the t-test, two-sample comparisons, linear mixed models, and Poisson mixed models by using existing software. Caveats and potential problems associated with Bayesian testing are also discussed. We aim to inform researchers in the many fields where Bayesian testing is not in common use of a well-developed alternative to null hypothesis significance testing and to demonstrate its standard implementation.

A Bayesian spatial model for imaging genetics.

We develop a Bayesian bivariate spatial model for multivariate regression analysis applicable to studies examining the influence of genetic variation on brain structure. Our model is motivated by an imaging genetics study of the Alzheimer's Disease Neuroimaging Initiative (ADNI), where the objective is to examine the association between images of volumetric and cortical thickness values summarizing the structure of the brain as measured by magnetic resonance imaging (MRI) and a set of 486 single nucleotide polymorphism (SNPs) from 33 Alzheimer's disease (AD) candidate genes obtained from 632 subjects. A bivariate spatial process model is developed to accommodate the correlation structures typically seen in structural brain imaging data. First, we allow for spatial correlation on a graph structure in the imaging phenotypes obtained from a neighborhood matrix for measures on the same hemisphere of the brain. Second, we allow for correlation in the same measures obtained from different hemispheres (left/right) of the brain. We develop a mean-field variational Bayes algorithm and a Gibbs sampling algorithm to fit the model. We also incorporate Bayesian false discovery rate (FDR) procedures to select SNPs. We implement the methodology in a new release of the R package bgsmtr. We show that the new spatial model demonstrates superior performance over a standard model in our application. Data used in the preparation of this article were obtained from the ADNI database (https://adni.loni.usc.edu).

Sparse Estimation Strategies in Linear Mixed Effect Models for High-Dimensional Data Application.

In a host of business applications, biomedical and epidemiological studies, the problem of multicollinearity among predictor variables is a frequent issue in longitudinal data analysis for linear mixed models (LMM). We consider an efficient estimation strategy for high-dimensional data application, where the dimensions of the parameters are larger than the number of observations. In this paper, we are interested in estimating the fixed effects parameters of the LMM when it is assumed that some prior information is available in the form of linear restrictions on the parameters. We propose the pretest and shrinkage estimation strategies using the ridge full model as the base estimator. We establish the asymptotic distributional bias and risks of the suggested estimators and investigate their relative performance with respect to the ridge full model estimator. Furthermore, we compare the numerical performance of the LASSO-type estimators with the pretest and shrinkage ridge estimators. The methodology is investigated using simulation studies and then demonstrated on an application exploring how effective brain connectivity in the default mode network (DMN) may be related to genetics within the context of Alzheimer's disease.

Ant Colony System Optimization for Spatiotemporal Modelling of Combined EEG and MEG Data.

Electroencephalography/Magnetoencephalography (EEG/MEG) source localization involves the estimation of neural activity inside the brain volume that underlies the EEG/MEG measures observed at the sensor array. In this paper, we consider a Bayesian finite spatial mixture model for source reconstruction and implement Ant Colony System (ACS) optimization coupled with Iterated Conditional Modes (ICM) for computing estimates of the neural source activity. Our approach is evaluated using simulation studies and a real data application in which we implement a nonparametric bootstrap for interval estimation. We demonstrate improved performance of the ACS-ICM algorithm as compared to existing methodology for the same spatiotemporal model.

Spectral dynamic causal modelling of resting-state fMRI: an exploratory study relating effective brain connectivity in the default mode network to genetics.

We conduct an imaging genetics study to explore how effective brain connectivity in the default mode network (DMN) may be related to genetics within the context of Alzheimer's disease and mild cognitive impairment. We develop an analysis of longitudinal resting-state functional magnetic resonance imaging (rs-fMRI) and genetic data obtained from a sample of 111 subjects with a total of 319 rs-fMRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. A Dynamic Causal Model (DCM) is fit to the rs-fMRI scans to estimate effective brain connectivity within the DMN and related to a set of single nucleotide polymorphisms (SNPs) contained in an empirical disease-constrained set which is obtained out-of-sample from 663 ADNI subjects having only genome-wide data. We relate longitudinal effective brain connectivity estimated using spectral DCM to SNPs using both linear mixed effect (LME) models as well as function-on-scalar regression (FSR). In both cases we implement a parametric bootstrap for testing SNP coefficients and make comparisons with p-values obtained from asymptotic null distributions. In both networks at an initial q-value threshold of 0.1 no effects are found. We report on exploratory patterns of associations with relatively high ranks that exhibit stability to the differing assumptions made by both FSR and LME.

A Review of Statistical Methods in Imaging Genetics.

With the rapid growth of modern technology, many biomedical studies are being conducted to collect massive datasets with volumes of multi-modality imaging, genetic, neurocognitive, and clinical information from increasingly large cohorts. Simultaneously extracting and integrating rich and diverse heterogeneous information in neuroimaging and/or genomics from these big datasets could transform our understanding of how genetic variants impact brain structure and function, cognitive function, and brain-related disease risk across the lifespan. Such understanding is critical for diagnosis, prevention, and treatment of numerous complex brain-related disorders (e.g., schizophrenia and Alzheimer's disease). However, the development of analytical methods for the joint analysis of both high-dimensional imaging phenotypes and high-dimensional genetic data, a big data squared (BD2) problem, presents major computational and theoretical challenges for existing analytical methods. Besides the high-dimensional nature of BD2, various neuroimaging measures often exhibit strong spatial smoothness and dependence and genetic markers may have a natural dependence structure arising from linkage disequilibrium. We review some recent developments of various statistical techniques for imaging genetics, including massive univariate and voxel-wise approaches, reduced rank regression, mixture models, and group sparse multi-task regression. By doing so, we hope that this review may encourage others in the statistical community to enter into this new and exciting field of research.

Time series analysis of fMRI data: Spatial modelling and Bayesian computation.

Time series analysis of fMRI data is an important area of medical statistics for neuroimaging data. Spatial models and Bayesian approaches for inference in such models have advantages over more traditional mass univariate approaches; however, a major challenge for such analyses is the required computation. As a result, the neuroimaging community has embraced approximate Bayesian inference based on mean-field variational Bayes (VB) approximations. These approximations are implemented in standard software packages such as the popular statistical parametric mapping software. While computationally efficient, the quality of VB approximations remains unclear even though they are commonly used in the analysis of neuroimaging data. For reliable statistical inference, it is important that these approximations be accurate and that users understand the scenarios under which they may not be accurate. We consider this issue for a particular model that includes spatially varying coefficients. To examine the accuracy of the VB approximation, we derive Hamiltonian Monte Carlo (HMC) for this model and conduct simulation studies to compare its performance with VB in terms of estimation accuracy, posterior variability, the spatial smoothness of estimated images, and computation time. As expected, we find that the computation time required for VB is considerably less than that for HMC. In settings involving a high or moderate signal-to-noise ratio (SNR), we find that the 2 approaches produce very similar results suggesting that the VB approximation is useful in this setting. On the other hand, when one considers a low SNR, substantial differences are found, suggesting that the approximation may not be accurate in such cases and we demonstrate that VB produces Bayes estimators with larger mean squared error. A comparison of the 2 computational approaches in an application examining the hemodynamic response to face perception in addition to a comparison with the traditional mass univariate approach in this application is also considered. Overall, our work clarifies the usefulness of VB for the spatiotemporal analysis of fMRI data, while also pointing out the limitation of VB when the SNR is low and the utility of HMC in this case.

Bayesian Computation for Log-Gaussian Cox Processes: A Comparative Analysis of Methods.

The Log-Gaussian Cox Process is a commonly used model for the analysis of spatial point pattern data. Fitting this model is difficult because of its doubly-stochastic property, i.e., it is an hierarchical combination of a Poisson process at the first level and a Gaussian Process at the second level. Various methods have been proposed to estimate such a process, including traditional likelihood-based approaches as well as Bayesian methods. We focus here on Bayesian methods and several approaches that have been considered for model fitting within this framework, including Hamiltonian Monte Carlo, the Integrated nested Laplace approximation, and Variational Bayes. We consider these approaches and make comparisons with respect to statistical and computational efficiency. These comparisons are made through several simulation studies as well as through two applications, the first examining ecological data and the second involving neuroimaging data.

A Bayesian group sparse multi-task regression model for imaging genetics.

MOTIVATION: Recent advances in technology for brain imaging and high-throughput genotyping have motivated studies examining the influence of genetic variation on brain structure. Wang et al. have developed an approach for the analysis of imaging genomic studies using penalized multi-task regression with regularization based on a novel group l2,1-norm penalty which encourages structured sparsity at both the gene level and SNP level. While incorporating a number of useful features, the proposed method only furnishes a point estimate of the regression coefficients; techniques for conducting statistical inference are not provided. A new Bayesian method is proposed here to overcome this limitation. RESULTS: We develop a Bayesian hierarchical modeling formulation where the posterior mode corresponds to the estimator proposed by Wang et al. and an approach that allows for full posterior inference including the construction of interval estimates for the regression parameters. We show that the proposed hierarchical model can be expressed as a three-level Gaussian scale mixture and this representation facilitates the use of a Gibbs sampling algorithm for posterior simulation. Simulation studies demonstrate that the interval estimates obtained using our approach achieve adequate coverage probabilities that outperform those obtained from the nonparametric bootstrap. Our proposed methodology is applied to the analysis of neuroimaging and genetic data collected as part of the Alzheimer's Disease Neuroimaging Initiative (ADNI), and this analysis of the ADNI cohort demonstrates clearly the value added of incorporating interval estimation beyond only point estimation when relating SNPs to brain imaging endophenotypes. AVAILABILITY AND IMPLEMENTATION: Software and sample data is available as an R package 'bgsmtr' that can be downloaded from The Comprehensive R Archive Network (CRAN). CONTACT: nathoo@uvic.ca. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A Skew-t space-varying regression model for the spectral analysis of resting state brain activity.

It is known that in many neurological disorders such as Down syndrome, main brain rhythms shift their frequencies slightly, and characterizing the spatial distribution of these shifts is of interest. This article reports on the development of a Skew-t mixed model for the spatial analysis of resting state brain activity in healthy controls and individuals with Down syndrome. Time series of oscillatory brain activity are recorded using magnetoencephalography, and spectral summaries are examined at multiple sensor locations across the scalp. We focus on the mean frequency of the power spectral density, and use space-varying regression to examine associations with age, gender and Down syndrome across several scalp regions. Spatial smoothing priors are incorporated based on a multivariate Markov random field, and the markedly non-Gaussian nature of the spectral response variable is accommodated by the use of a Skew-t distribution. A range of models representing different assumptions on the association structure and response distribution are examined, and we conduct model selection using the deviance information criterion. (1) Our analysis suggests region-specific differences between healthy controls and individuals with Down syndrome, particularly in the left and right temporal regions, and produces smoothed maps indicating the scalp topography of the estimated differences.

Skew-elliptical spatial random effect modeling for areal data with application to mapping health utilization rates.

Mixed models incorporating spatially correlated random effects are often used for the analysis of areal data. In this setting, spatial smoothing is introduced at the second stage of a hierarchical framework, and this smoothing is often based on a latent Gaussian Markov random field. The Markov random field provides a computationally convenient framework for modeling spatial dependence; however, the Gaussian assumption underlying commonly used models can be overly restrictive in some applications. This can be a problem in the presence of outliers or discontinuities in the underlying spatial surface, and in such settings, models based on non-Gaussian spatial random effects are useful. Motivated by a study examining geographic variation in the treatment of acute coronary syndrome, we develop a robust model for smoothing small-area health service utilization rates. The model incorporates non-Gaussian spatial random effects, and we develop a formulation for skew-elliptical areal spatial models. We generalize the Gaussian conditional autoregressive model to the non-Gaussian case, allowing for asymmetric skew-elliptical marginal distributions having flexible tail behavior. The resulting new models are flexible, computationally manageable, and can be implemented in the standard Bayesian software WinBUGS. We demonstrate performance of the proposed methods and comparisons with other commonly used Gaussian and non-Gaussian spatial prior formulations through simulation and analysis in our motivating application, mapping rates of revascularization for patients diagnosed with acute coronary syndrome in Quebec, Canada.

A Bayesian space-time model for discrete spread processes on a lattice.

In this article we present a Bayesian Markov model for investigating environmental spread processes. We formulate a model where the spread of a disease over a heterogeneous landscape through time is represented as a probabilistic function of two processes: local diffusion and random-jump dispersal. This formulation represents two mechanisms of spread which result in highly peaked and long-tailed distributions of dispersal distances (i.e., local and long-distance spread), commonly observed in the spread of infectious diseases and biological invasions. We demonstrate the properties of this model using a simulation experiment and an empirical case study - the spread of mountain pine beetle in western Canada. Posterior predictive checking was used to validate the number of newly inhabited regions in each time period. The model performed well in the simulation study in which a goodness-of-fit statistic measuring the number of newly inhabited regions in each time interval fell within the 95% posterior predictive credible interval in over 97% of simulations. The case study of a mountain pine beetle infestation in western Canada (1999-2009) extended the base model in two ways. First, spatial covariates thought to impact the local diffusion parameters, elevation and forest cover, were included in the model. Second, a refined definition for translocation or jump-dispersal based on mountain pine beetle ecology was incorporated improving the fit of the model. Posterior predictive checks on the mountain pine beetle model found that the observed goodness-of-fit test statistic fell within the 95% posterior predictive credible interval for 8 out of 10 years. The simulation study and case study provide evidence that the model presented here is both robust and flexible; and is therefore appropriate for a wide range of spread processes in epidemiology and ecology.